A Neural Network-Based Dynamic Cost Function for the Implementation of a Predictive Current Controller

Machado, Osmell; Martín, Pedro Sánchez; Rodríguez, Francisco

doi:10.1109/tii.2017.2691461

Cited by 79 publications

(36 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid heuristics, there have been some methods that choose the weighting factors based on analytical expressions, thus avoiding tuning altogether [115], [151], [152]. Moreover, emerging methods for the weighting factors tuning utilize techniques from artificial intelligence, such as neural networks and genetic algorithms [143], [153]- [155]. In this way the tuning process is automated and the weighting factors can be adjusted in real time.…”

Section: B Tuning Parametersmentioning

confidence: 99%

Model Predictive Control of Power Electronic Systems: Methods, Results, and Challenges

Καραμανάκος

Liegmann

Geyer

et al. 2020

IEEE Open J. Ind. Applicat.

300

130

View full text Add to dashboard Cite

Model predictive control (MPC) has established itself as a promising control methodology in power electronics. This survey paper highlights the most relevant MPC techniques for power electronic systems. These can be classified into two major groups, namely, MPC without modulator, referred to as direct MPC, and MPC with a subsequent modulation stage, known as indirect MPC. Design choices and parameters that affect the system performance, closed-loop stability and controller robustness are discussed. Moreover, solvers and control platforms that can be employed for the real-time implementation of MPC algorithms are presented. Finally, the MPC schemes in question are assessed, among others, in terms of design and computational complexity, along with their performance and applicability depending on the power electronic system at hand.

show abstract

Section: B Tuning Parametersmentioning

confidence: 99%

Model Predictive Control of Power Electronic Systems: Methods, Results, and Challenges

Καραμανάκος

Liegmann

Geyer

et al. 2020

IEEE Open J. Ind. Applicat.

300

130

View full text Add to dashboard Cite

show abstract

“…In the proposed method, the weighting factors can be dynamically adjusted online by using a fuzzy logic control technique, and thus, the satisfactory system control performance can be obtained. In [18], a novel tuning procedure based on neural network for the weighting factors is presented. In this proposed approach, the weighting factors in the cost function can be adaptively updated online.…”

Section: Introductionmentioning

confidence: 99%

Passivity-Based Cascade-Free Finite-Set Model Predictive Control for Nested Neutral Point-Clamped Converters

Qiu

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

This paper focuses on a novel passivity-based cascade-free finite-control-set model predictive control scheme (CFFCS-MPC) for nested neutral point-clamped converters (NNPCs). It can be realized by combining an FCS-MPC and a passivity-based dynamic reference design point of view, which is responsible for controlling the multi-objective optimization control problem based on a cascade-free structure without weighting factors. However, it is of importance to highlight that, due to the existence of a large number of switching combinations and redundancies, the online computational effort will be increased by employing the proposed CFFCS-MPC approach, especially for higher-level power converter topologies. To solve this issue, a simplified computational scheme is presented by introducing the passivity-based dynamic reference concept into the design of sector distribution method. Alternatively, a simplified cost function based on the reference output voltage-vector tracking error is embedded into the proposed design. The merits of the proposed solution summarized as follows: 1) Enhanced system robustness; 2) no weighting factors; 3) high dynamics; and 4) low computational complexity. Finally, the proposed methodology is verified analytically and confirmed by comprehensive results that prove the theoretical investigations. INDEX TERMS Passivity-based cascade-free finite-control-set model predictive control, dynamic reference design, cost function, weighting factors.

show abstract

“…Zhang et al considered the finite set model predictive control scheme with an optimal switching voltage vector technique for high-performance ipmsm drive applications [21] . Machado et al proposed a neural networkbased dynamic cost function for the implementation of a predictive current controller with several control targets and constraints can be included in a cost function [22] . Singh and Choi describe the status of marine current power generation technology, and their result mainly describes the advantages and disadvantages of tidal turbine technology [23] .…”

Section: Introductionmentioning

confidence: 99%

Optimal Control Design of Generator Systems for Marine Current Turbine Applications Using Economic Model Predictive Control

Teng

2020

IEEE Access

View full text Add to dashboard Cite

A Neural Network-Based Dynamic Cost Function for the Implementation of a Predictive Current Controller

Cited by 79 publications

References 25 publications

Model Predictive Control of Power Electronic Systems: Methods, Results, and Challenges

Model Predictive Control of Power Electronic Systems: Methods, Results, and Challenges

Passivity-Based Cascade-Free Finite-Set Model Predictive Control for Nested Neutral Point-Clamped Converters

Optimal Control Design of Generator Systems for Marine Current Turbine Applications Using Economic Model Predictive Control

Contact Info

Product

Resources

About